Example #1
0
File: detenc.c Project: udev/detenc
int main (int argc, char **argv) {
  FILE *fp;
  int quiet = 0;
  int show_offset = 0;
  int opt;
  int i;
  char *filename;
  const char *encoding;

  while ((opt = getopt(argc, argv, "oqh")) != -1) {
    switch (opt) {
      case 'o':
        show_offset = 1;
        break;
      case 'q':
        quiet = 1;
        break;
      case 'h':
        show_usage();
        return 0;
      default:
        fprintf(stderr, "Unknown option -%c", opt);
        show_usage();
        return 1;
    }
  }

  if (optind == argc) {
    fprintf(stderr, "No files specified.\n");
    show_usage();
    return 1;
  }

  for (i = optind; i < argc; i++) {
    filename = argv[i];
    fp = fopen(filename, "rb");

    if (fp == NULL) {
      fprintf(stderr, "Can't open file '%s' for reading.\n", filename);
    } else {
      if (!quiet)
        printf("%s: ", filename);
      encoding = detect_encoding(fp);
      printf("%s", encoding);
      if (show_offset && strcmp("UNKNOWN", encoding) == 0)
        printf(" near offset %ld (0x%lX)", (long)ftell(fp), (long)ftell(fp));
      printf("\n");
      fclose(fp);
    }
  }

  return 0;
}
Example #2
0
File: buffer.c Project: dmt4/ne
encoding_type detect_buffer_encoding(const buffer * const b) {
	line_desc *ld = (line_desc *)b->line_desc_list.head, *next;
	encoding_type encoding = ENC_ASCII, e;

	while(next = (line_desc *)ld->ld_node.next) {
		e = detect_encoding(ld->line, ld->line_len);
		if (e != ENC_ASCII) {
			if (encoding == ENC_ASCII) encoding = e;
			if (e == ENC_8_BIT) encoding = ENC_8_BIT;
		}
		ld = next;
	}

	return encoding;
}
Example #3
0
static HRESULT read_xml(const WCHAR *name, WCHAR **xml)
{
    HANDLE hfile;
    DWORD size, attrs;
    char *src;
    int cp;

    attrs = GetFileAttributesW(name);
    if (attrs == INVALID_FILE_ATTRIBUTES)
        return HRESULT_FROM_WIN32(GetLastError());
    if (attrs & FILE_ATTRIBUTE_DIRECTORY)
        return HRESULT_FROM_WIN32(ERROR_PATH_NOT_FOUND);

    hfile = CreateFileW(name, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, 0, 0);
    if (hfile == INVALID_HANDLE_VALUE)
        return HRESULT_FROM_WIN32(GetLastError());

    size = GetFileSize(hfile, NULL);
    src = heap_alloc(size + 2);
    if (!src)
    {
        CloseHandle(hfile);
        return E_OUTOFMEMORY;
    }

    src[size] = 0;
    src[size + 1] = 0;

    ReadFile(hfile, src, size, &size, NULL);
    CloseHandle(hfile);

    cp = detect_encoding(src, size);
    if (cp < 0)
    {
        *xml = (WCHAR *)src;
        return S_OK;
    }

    if (cp == CP_UTF8 && size >= sizeof(bom_utf8) && !memcmp(src, bom_utf8, sizeof(bom_utf8)))
        src += sizeof(bom_utf8);

    size = MultiByteToWideChar(cp, 0, src, -1, NULL, 0);
    *xml = heap_alloc(size * sizeof(WCHAR));
    if (!*xml) return E_OUTOFMEMORY;
    MultiByteToWideChar(cp, 0, src, -1, *xml, size);
    return S_OK;
}
Example #4
0
static HRESULT read_xml(const WCHAR *name, WCHAR **xml)
{
    HANDLE hfile;
    DWORD size;
    char *src;
    int cp;

    hfile = CreateFileW(name, GENERIC_READ, FILE_SHARE_READ, NULL, OPEN_EXISTING, 0, 0);
    if (hfile == INVALID_HANDLE_VALUE)
        return HRESULT_FROM_WIN32(GetLastError());

    size = GetFileSize(hfile, NULL);
    src = heap_alloc(size + 2);
    if (!src)
    {
        CloseHandle(hfile);
        return E_OUTOFMEMORY;
    }

    src[size] = 0;
    src[size + 1] = 0;

    ReadFile(hfile, src, size, &size, NULL);
    CloseHandle(hfile);

    cp = detect_encoding(src, size);
    if (cp < 0)
    {
        *xml = (WCHAR *)src;
        return S_OK;
    }

    size = MultiByteToWideChar(cp, 0, src, -1, NULL, 0);
    *xml = heap_alloc(size * sizeof(WCHAR));
    if (!*xml) return E_OUTOFMEMORY;
    MultiByteToWideChar(cp, 0, src, -1, *xml, size);
    return S_OK;
}
Example #5
0
File: streams.c Project: dmt4/ne
void set_stream_encoding(char_stream * const cs, const encoding_type source) {
	cs->encoding = detect_encoding(cs->stream, cs->len);
	if (source == ENC_8_BIT && cs->encoding == ENC_UTF8) cs->encoding = ENC_8_BIT;
}
Example #6
0
File: input.c Project: dmt4/ne
char *request(const char *prompt, const char * const default_string, const bool alpha_allowed, const int completion_type, const bool prefer_utf8) {

	set_attr(0);

	input_buffer[pos = len = offset = 0] = 0;
	encoding = ENC_ASCII;
	x = start_x = print_prompt(prompt);

	init_history();

	if (default_string) {
		strncpy(input_buffer, default_string, MAX_INPUT_LINE_LEN);
		len = strlen(input_buffer);
		encoding = detect_encoding(input_buffer, len);
		input_refresh();
	}

	bool first_char_typed = true, last_char_completion = false, selection = false;

	while(true) {

		assert(input_buffer[len] == 0);

		move_cursor(ne_lines - 1, x);

		int c;
		input_class ic;
		do c = get_key_code(); while((ic = CHAR_CLASS(c)) == IGNORE);

		/* ISO 10646 characters *above 256* can be added only to UTF-8 lines, or ASCII lines (making them, of course, UTF-8). */
		if (ic == ALPHA && c > 0xFF && encoding != ENC_ASCII && encoding != ENC_UTF8) ic = INVALID;

		if (ic != TAB) last_char_completion = false;
		if (ic == TAB && !completion_type) ic = ALPHA;

		switch(ic) {

		case INVALID:
			alert();
			break;

		case ALPHA:

			if (first_char_typed) {
				input_buffer[len = 0] = 0;
				clear_to_eol();
			}

			if (encoding == ENC_ASCII && c > 0x7F) encoding = prefer_utf8 || c > 0xFF ? ENC_UTF8 : ENC_8_BIT;
			int c_len = encoding == ENC_UTF8 ? utf8seqlen(c) : 1;
			int c_width = output_width(c);
			assert(c_len > 0);

			if (len <= MAX_INPUT_LINE_LEN - c_len && (alpha_allowed || (c < 0x100 && isxdigit(c)) || c=='X' || c=='x')) {

				memmove(&input_buffer[pos + c_len], &input_buffer[pos], len - pos + 1);

				if (c_len == 1) input_buffer[pos] = c;
				else utf8str(c, &input_buffer[pos]);

				len += c_len;

				move_cursor(ne_lines - 1, x);

				if (x < ne_columns - c_width) {
					if (pos == len - c_len) output_char(c, 0, encoding);
					else if (char_ins_del_ok) insert_char(c, 0, encoding);
					else input_refresh();
				}

				input_move_right(true);
			}
			break;

		case RETURN:
			selection = true;
			break;

		case TAB:
			if (completion_type == COMPLETE_FILE || completion_type == COMPLETE_SYNTAX) {
				bool quoted = false;
				char *prefix, *completion, *p;
				if (len && input_buffer[len - 1] == '"') {
					input_buffer[len - 1] = 0;
					if (prefix = strrchr(input_buffer, '"')) {
						quoted = true;
						prefix++;
					}
					else input_buffer[len - 1] = '"';
				}

				if (!quoted) {
					prefix = strrchr(input_buffer, ' ');
					if (prefix) prefix++;
					else prefix = input_buffer;
				}

				if (last_char_completion || completion_type == COMPLETE_SYNTAX) {
					if (completion_type == COMPLETE_FILE )
						completion = p = request_files(prefix, true);
					else
						completion = p = request_syntax(prefix, true);
					reset_window();
					if (completion) {
						if (*completion) selection = true;
						else completion++;
					}
				}
				else {
					if (completion_type == COMPLETE_FILE )
						completion = p = complete_filename(prefix);
					else
						completion = p = request_syntax(prefix, true);
					last_char_completion = true;
					if (!completion) alert();
				}

				if (completion && (prefix - input_buffer) + strlen(completion) + 1 < MAX_INPUT_LINE_LEN) {
					const encoding_type completion_encoding = detect_encoding(completion, strlen(completion));
					if (encoding == ENC_ASCII || completion_encoding == ENC_ASCII || encoding == completion_encoding) {
						strcpy(prefix, completion);
						if (quoted) strcat(prefix, "\"");
						len = strlen(input_buffer);
						pos = offset = 0;
						x = start_x;
						if (encoding == ENC_ASCII) encoding = completion_encoding;
						input_move_to_eol();
						if (quoted) input_move_left(false);
						input_refresh();
					}
					else alert();
				}
				else if (quoted) strcat(prefix, "\"");

				free(p);
			}
			break;

		case COMMAND:
			if (c < 0) c = -c - 1;
			const int a = parse_command_line(key_binding[c], NULL, NULL, false);
			if (a >= 0) {
				switch(a) {

				case LINEUP_A:
				case LINEDOWN_A:
				case MOVESOF_A:
				case MOVEEOF_A:
				case PAGEUP_A:
				case PAGEDOWN_A:
				case NEXTPAGE_A:
				case PREVPAGE_A:
					if (history_buff) {
						switch(a) {
						case LINEUP_A: line_up(history_buff); break;
						case LINEDOWN_A: line_down(history_buff); break;
						case MOVESOF_A: move_to_sof(history_buff); break;
						case MOVEEOF_A: move_to_bof(history_buff); break;
						case PAGEUP_A:
						case PREVPAGE_A: prev_page(history_buff); break;
						case PAGEDOWN_A:
						case NEXTPAGE_A: next_page(history_buff); break;
						}

						/* In some cases, the default displayed on the command line will be the same as the 
							first history item. In that case we skip it. */

						if (first_char_typed == true 
							 && a == LINEUP_A 
							 && history_buff->cur_line_desc->line 
							 && !strncmp(history_buff->cur_line_desc->line, input_buffer, history_buff->cur_line_desc->line_len))
							line_up(history_buff);

						if (history_buff->cur_line_desc->line) {
							strncpy(input_buffer,
									  history_buff->cur_line_desc->line,
									  min(history_buff->cur_line_desc->line_len,MAX_INPUT_LINE_LEN));
							input_buffer[min(history_buff->cur_line_desc->line_len,MAX_INPUT_LINE_LEN)] = 0;
							len	 = strlen(input_buffer);
							encoding = detect_encoding(input_buffer, len);
						}
						else {
							input_buffer[len = 0] = 0;
							encoding = ENC_ASCII;
						}

						x		= start_x;
						pos	= 0;
						offset = 0;
						input_refresh();
					}
					break;

				case MOVELEFT_A:
					input_move_left(true);
					break;

				case MOVERIGHT_A:
					input_move_right(true);
					break;

				case BACKSPACE_A:
					if (pos == 0) break;
					input_move_left(true);

				case DELETECHAR_A:
					if (len > 0 && pos < len) {
						int c_len = encoding == ENC_UTF8 ? utf8len(input_buffer[pos]) : 1;
						int c_width = get_char_width(&input_buffer[pos], encoding);
						memmove(&input_buffer[pos], &input_buffer[pos + c_len], len - pos - c_len + 1);
						len -= c_len;
						if (input_buffer_is_ascii()) encoding = ENC_ASCII;

						if (char_ins_del_ok) {
							int i, j;

							move_cursor(ne_lines - 1, x);
							delete_chars(c_width);

							for(i = x, j = pos; j < len && i + get_char_width(&input_buffer[j], encoding) < ne_columns - c_width; i += get_char_width(&input_buffer[j], encoding), j = next_pos(input_buffer, j, encoding));

							if (j < len) {
								move_cursor(ne_lines - 1, i);
								while(j < len && i + get_char_width(&input_buffer[j], encoding) < ne_columns) {
									output_char(get_char(&input_buffer[j], encoding), 0, encoding);
									i += get_char_width(&input_buffer[j], encoding);
									j = next_pos(input_buffer, j, encoding);
								}
							}
						}
						else input_refresh();
					}
					break;

				case DELETELINE_A:
					move_cursor(ne_lines - 1, start_x);
					clear_to_eol();
					input_buffer[len = pos = offset = 0] = 0;
					encoding = ENC_ASCII;
					x = start_x;
					break;

				case DELETEEOL_A:
					input_buffer[len = pos] = 0;
					clear_to_eol();
					if (input_buffer_is_ascii()) encoding = ENC_ASCII;
					break;

				case MOVEINCUP_A:
					if (x != start_x) {
						pos = offset;
						x = start_x;
						break;
					}

				case MOVESOL_A:
					input_move_to_sol();
					break;

				case MOVEINCDOWN_A: {
					int i, j;
					for(i = x, j = pos; j < len && i + get_char_width(&input_buffer[j], encoding) < ne_columns; i += get_char_width(&input_buffer[j], encoding), j = next_pos(input_buffer, j, encoding));
					if (j != pos && j < len) {
						pos = j;
						x = i;
						break;
					}
				}

				case MOVEEOL_A:
					input_move_to_eol();
					break;

				case TOGGLESEOL_A:
				case TOGGLESEOF_A:
					if (pos != 0) input_move_to_sol();
					else input_move_to_eol();
					break;

				case PREVWORD_A:
					input_prev_word();
					break;

				case NEXTWORD_A:
					input_next_word();
					break;

				case REFRESH_A:
					input_refresh();
					break;

				case PASTE_A:
					input_paste();
					break;

				case AUTOCOMPLETE_A:
					input_autocomplete();
					break;

				case ESCAPE_A:
					return NULL;

				default:
					break;
				}
			}
			break;

		default:
			break;
		}

		if (selection) {
			const line_desc * const last = (line_desc *)history_buff->line_desc_list.tail_pred->prev;
			assert(input_buffer[len] == 0);
			if (history_buff->num_lines == 0 || len != last->line_len || strncmp(input_buffer, last->line, last->line_len)) add_to_history(input_buffer);
			return input_buffer;
		}

		first_char_typed = false;
	}
}
Example #7
0
File: input.c Project: dmt4/ne
static void input_autocomplete(void) {
	int dx = 0, prefix_pos = pos;
	char *p;

	/* find a usable prefix */
	if (prefix_pos && prefix_pos <= len) {
		prefix_pos = prev_pos(input_buffer, prefix_pos, encoding);
		dx--;
		while (prefix_pos && ne_isword(get_char(&input_buffer[prefix_pos], encoding), encoding)) {
			dx--;
			prefix_pos = prev_pos(input_buffer, prefix_pos, encoding);
		}
		if (! ne_isword(get_char(&input_buffer[prefix_pos], encoding), encoding)) {
			dx++;
			prefix_pos = next_pos(input_buffer, prefix_pos, encoding);
		}
		p = malloc(pos - prefix_pos + 1);
		if (!p) {
			alert(); /* OUT_OF_MEMORY */
			return;
		}
		strncpy(p, &input_buffer[prefix_pos], pos - prefix_pos);
	}
	else p = malloc(1); /* no prefix left of the cursor; we'll give an empty one. */
	p[pos - prefix_pos] = 0;

	int ac_err;
	if (p = autocomplete(p, NULL, true, &ac_err)) {
		encoding_type ac_encoding = detect_encoding(p, strlen(p));
		if (ac_encoding != ENC_ASCII && encoding != ENC_ASCII && ac_encoding != encoding) {
			free(p);
			alert();
		} else {
			encoding = ac_encoding;

			if (prefix_pos < pos) {
				memmove(&input_buffer[prefix_pos], &input_buffer[pos], len - pos + 1);
				len -= pos - prefix_pos;
				pos = prefix_pos;
			}
			int ac_len = strlen(p);
			if (ac_len + len >= MAX_INPUT_LINE_LEN) ac_len = MAX_INPUT_LINE_LEN - len;
			memmove(&input_buffer[pos + ac_len], &input_buffer[pos], len - pos + 1);
			memmove(&input_buffer[pos], p, ac_len);
			len += ac_len;
			while (ac_len > 0) {
				const int cw = get_char_width(&input_buffer[pos],encoding);
				pos = next_pos(input_buffer, pos, encoding);
				ac_len -= cw;
				dx++;
			}
			free(p); 
			x += dx;
			if (x >= ne_columns) {
				dx = x - ne_columns + 1;
				while (dx--) {
					offset = next_pos(input_buffer, offset, encoding);
				}
				x = ne_columns - 1;
			}
		}
	}
	if (ac_err == AUTOCOMPLETE_COMPLETED || ac_err == AUTOCOMPLETE_CANCELLED) {
		do_action(cur_buffer, REFRESH_A, 0, NULL);
		refresh_window(cur_buffer);
		set_attr(0);
		print_prompt(NULL);
	}
	input_refresh();
}